Smooth object retrieval using a bag of boundaries by Arandjelović, R, Zisserman, A

“…The descriptors are tolerant to scale changes, segmentation failures, and limited viewpoint changes. …”

Semantic scene understanding on 3D point clouds by Dong, Shichao

“…Using regional purity can simultaneously prevent under-segmentation and over-segmentation problems during clustering. …”
Get full text

Image processing using neural network for auto-scoring system by Ruan, Zhendui.

“…Image processing comprises of image retrieval, segmentation and features extraction as well as classical statistical and modern classification techniques. …”
Get full text

What Singapore investors want in a financial adviser by Chen, Carolyn Meijun, Fang, Mindy Liwei, Lim, Karen Lee Mei

“…This will provide an insight to the criteria financial advisers should focus on as well as the market segment that emerging independent financial advisers should target.…”
Get full text

Exposing digital image forgeries by detecting discrepancies in motion blur by Kakar, Pravin, Ser, Wee, Sudha, N.

“…Experimental results show that our technique provides good segmentation of regions with inconsistent motion blur. …”
Get full text
Get full text

Singapore airlines : the business of flying by Tan, Sung Cheng, Tan, Ting Szu, Tie, Hwee Ling

“…Due to the possible extend of scope, the study is focused on the segment of business air travellers.…”
Get full text

Employee turnover : bad attitude or poor management? by Khadijah Abdul Rahman., Norfarhana Supaat., Norhayati Haron.

“…The variables for the turnover are segmented into three categories - controllable, uncontrollable and demographics.…”
Get full text

Automatic cardiac ventricular boundary detection by Cheng, Jierong

“…The final segmentation to find the actual LV boundary in long-axis echocardiographic images is carried out using a Markovian level set method. …”
Get full text

The truth about cats and dogs by Parkhi, O, Vedaldi, A, Jawahar, C, Zisserman, A

“…In these cases we propose to use the template-based model to detect a distinctive part for the class, followed by detecting the rest of the object via segmentation on image specific information learnt from that part. …”

Unsupervised discovery of visual object class hierarchies by Sivic, J, Russell, BC, Zisserman, A, Freeman, WT, Efros, AA

“…Employing the multiple segmentation framework of Russell et al. [22], we show that meaningful object hierarchies, together with object segmentations, can be automatically learned from unlabeled and unsegmented image collections without supervision. …”

Pursuing business opportunities in life sciences logistics in Vietnam : a case study of TNT by Chang, Meng Yi, Khoo, Malinda, Indrawati, Marini, Regina

“…This paper attempts to understand how TNT introduces a new service offering, the Clinical Express service, for a niche market segment, the life sciences industry, and how TNT exploits the opportunities available to launch the new service offering in a specific market, Vietnam.…”
Get full text

Extremely versatile deformability beyond materiality : a new material platform through simple cutting for rugged batteries by Kim, Kee-Bum, Lee, Young-Joo, Costa, Avelino, Lee, Yu-Ki, Jang, Tae-Sik, Lee, Myoung-Gyu, Joo, Young-Chang, Oh, Kyu Hwan, Song, Juha, Choi, In-Suk

“…The hierarchy and number of segmentations are the key parameters of the deformation mechanism for auxetic cut shape-reconfigurable battery systems. …”
Get full text

Elementwise overparameterisation for single and multi-task learning by Ribli, Vincent

“…In the field of autonomous vehicles, computer vision is used to solve multiple tasks such as semantic segmentation and object tracking. This can be challenging as the tasks need to be done at a high performance within a given latency threshold. …”
Get full text

Automatic and efficient long term arm and hand tracking for continuous sign language TV broadcasts by Pfister, T, Charles, J, Everingham, M, Zisserman, A

“…<br> Our contributions are (i) a co-segmentation algorithm that automatically separates the signer from any signed TV broadcast using a generative layered model; (ii) a method of predicting joint positions given only the segmentation and a colour model using a random forest regressor; and (iii) demonstrating that the random forest can be trained from an existing semi-automatic, but computationally expensive, tracker. …”

Discovering objects and their location in images by Sivic, J, Russell, BC, Efros, AA, Zisserman, A, Freeman, WT

“…It is demonstrated that this extended vocabulary gives a cleaner image segmentation. Finally, the classification and segmentation methods are applied to a set of images containing multiple objects per image. …”

Development of a vision-based gesture human-computer interface by Lim, Chun Ping.

“…With a few reasonable assumptions, this stage was achieved with 3 image processing techniques, namely background subtraction by codebook method, skin segmentation and contour convexity finding. To enhance the robustness of the system, a variant codebook method had been created to be used in skin segmentation. …”
Get full text

Hardware efficient algorithms and architectures for burst communications in cognitive radios by Syed Naveen Altaf Ahmed

“…To evaluate the proposed segmented schemes in terms of implementation hardware complexity, FPGA synthesis is conducted and results are presented.…”
Get full text

Purchasing behaviour of the Japanese visitors, an application of the theory of planned behaviour. by Yong, Yoon Mei.

“…Japanese visitors are an important segment of visitors that have contributed significantly to Singapore's annual receipts of visitors' expenditures. …”
Get full text

Design and development of image processing algorithms for quantitative road traffic data analysis by Krishnalal Puthiya Veettil.

“…Results comparison between different segmentation methods was performed to check the best detection method. …”
Get full text

Investigation of the image processing algorithms for medical applications by Nurul Hidayah Abdul Manan

“…Different segmentation techniques are used (i.e. K-means clustering, Fuzzy-C means clustering and Hierarchical clustering) to evaluate the performance.…”
Get full text